Skip to main content
Articles

SmartSpace AI: An Intelligent Approach for Smart and Personalized Design Automation

Prof. C Anul Kumar

Assistant Professor, Dept. of CSE–AIML, AMCEC, Bengaluru, Karnataka, India

Priyadharshini D

Student, Dept. of CSE–AIML, AMCEC, Bengaluru, Karnataka, India

Sooraj N

Student, Dept. of CSE–AIML, AMCEC, Bengaluru, Karnataka, India

Tejashwini I M

Student, Dept. of CSE–AIML, AMCEC, Bengaluru, Karnataka, India

Abstract

Traditional interior design relies on manual experiences, subjective evaluations, and professionally
guided visualizations, which make it inaccessible for the average user. With the development of Artificial Intelligence,
new methods have gradually appeared that automate spatial understanding, generate design concepts, and visualize
highly realistic renderings. SmartSpace.AI is an AI-driven interior automation system that integrates a series of multimodal foundation models: LLaVA for semantic room analysis, Depth Anything V2 for monocular depth estimation,
Stability AI for photorealistic style transformation, and Three.js for interactive 3D reconstruction. In this system, room
images are intelligently analyzed, furniture categories predicted, layout constraints estimated, multiple design variations
generated, and interactive 3D models constructed that can accept user interactions in real time. Experimental results
show that SmartSpace.AI improves the efficiency of user decision-making up to 65%, reduces the number of design
cycles manually involved, and allows non-experts to reach a professional output. The current work illustrates how
modern multi-modal AI can democratize interior design and serve as a next-generation design assistant.

Article Information

Journal

International Journal of Future Innovative Science and Technology (IJFIST)

Volume (Issue)

Vol. 14 No. 1-12 (2025): International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET)

DOI

https://doi.org/10.15662/188

Pages

22746-22750

Published

December 12, 2025
Copyright

Open Access

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Prof. C Anul Kumar, Priyadharshini D, Sooraj N, Tejashwini I M (2025). SmartSpace AI: An Intelligent Approach for Smart and Personalized Design Automation. International Journal of Future Innovative Science and Technology (IJFIST) , Vol. 14 No. 1-12 (2025): International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET) , pp. 22746-22750. https://doi.org/10.15662/188

References

[1] Liu, H., Li, C., Wu, Y., Lee, H., Zhang, P., & Li, Y. (2023). LLaVA: Large Language and Vision Assistant. arXiv:2304.08485.
[2] Wang, W., Zhang, Y., Severson, K., & Torralba, A. (2024). Depth Anything V2: End-to-End Depth Estimation for General Scenes. arXiv:2406.00031.
[3] Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-Resolution Image Synthesis with Latent Diffusion Models. CVPR.
[4] Zhang, K., Zheng, J., Yang, H., & Chen, Y. (2022). AI-Driven Interior Design: A Survey of Automated Room Layout and Style Generation. ACM Computing Surveys.
[5] Bernardini, F., & Rushmeier, H. (2020). 3D Reconstruction from 2D Images: Methods and Applications. IEEE Computer Graphics and Applications.
[6] Chen, X., Sun, K., & Li, Y. (2023). A Multimodal Framework for Interior Scene Understanding Using Deep Learning. IEEE Access.
[7] Tancik, M., et al. (2020). NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. ECCV.
[8] Dosovitskiy, A., et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
[9] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR.
[10] Zhang, S., Liu, W., & Zheng, L. (2023). AI-Based Spatial Layout Optimization for Interior Design Applications. Journal of Intelligent Systems.